The Agent Skills Directory

[SAFE]: The skill defines a structured workflow for a coding assistant to handle specialized RTX Sensor Processing Graph (SPG) assets. Analysis of the instructions and metadata revealed no evidence of malicious patterns, unauthorized downloads, or exfiltration.
[PROMPT_INJECTION]: The skill facilitates reading and editing local repository files, which constitutes a potential surface for indirect prompt injection if the files being processed contain adversarial content. * Ingestion points: Local repository sources such as docs/spg/index.rst and files under examples/python/spg-*. * Boundary markers: None specified in the instructions. * Capability inventory: The agent is granted Read, Grep, Write, and Edit tools. * Sanitization: No specific content validation or sanitization steps are defined.

spg-usd-lua-authoring